Abstract
For many problems in machine learning fields, the data are nonlinearly distributed. One popular way to tackle this kind of data is training a local kernel machine or a mixture of several locally linear models. However, both of these approaches heavily relies on local information, such as neighbor relations of each data sample, to capture potential data distribution. In this paper, we show the non-local information is more efficient for data representation. With an implementation of a winner-take-all autoencoder, several non-local templates are trained to trace the data distribution and to represent each sample in different subspaces with a suitable weight. By training a linear model for each subspace in a divide and conquer manner, one single support vector machine can be formulated to solve nonlinear classification problems. Experimental results demonstrate that a mixture of multiple linear classifiers from non-local information performs better than or is at least competitive with state-of-the-art mixtures of locally linear models.
| Original language | English |
|---|---|
| Title of host publication | 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 3741-3746 |
| Number of pages | 6 |
| Volume | 2017-May |
| ISBN (Electronic) | 9781509061815 |
| DOIs | |
| Publication status | Published - 2017 Jun 30 |
| Event | 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Anchorage, United States Duration: 2017 May 14 → 2017 May 19 |
Other
| Other | 2017 International Joint Conference on Neural Networks, IJCNN 2017 |
|---|---|
| Country | United States |
| City | Anchorage |
| Period | 17/5/14 → 17/5/19 |
Fingerprint
ASJC Scopus subject areas
- Software
- Artificial Intelligence
Cite this
Non-local information for a mixture of multiple linear classifiers. / Li, Weite; Liang, Peifeng; Yuan, Xin; Furuzuki, Takayuki.
2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Vol. 2017-May Institute of Electrical and Electronics Engineers Inc., 2017. p. 3741-3746 7966327.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Non-local information for a mixture of multiple linear classifiers
AU - Li, Weite
AU - Liang, Peifeng
AU - Yuan, Xin
AU - Furuzuki, Takayuki
PY - 2017/6/30
Y1 - 2017/6/30
N2 - For many problems in machine learning fields, the data are nonlinearly distributed. One popular way to tackle this kind of data is training a local kernel machine or a mixture of several locally linear models. However, both of these approaches heavily relies on local information, such as neighbor relations of each data sample, to capture potential data distribution. In this paper, we show the non-local information is more efficient for data representation. With an implementation of a winner-take-all autoencoder, several non-local templates are trained to trace the data distribution and to represent each sample in different subspaces with a suitable weight. By training a linear model for each subspace in a divide and conquer manner, one single support vector machine can be formulated to solve nonlinear classification problems. Experimental results demonstrate that a mixture of multiple linear classifiers from non-local information performs better than or is at least competitive with state-of-the-art mixtures of locally linear models.
AB - For many problems in machine learning fields, the data are nonlinearly distributed. One popular way to tackle this kind of data is training a local kernel machine or a mixture of several locally linear models. However, both of these approaches heavily relies on local information, such as neighbor relations of each data sample, to capture potential data distribution. In this paper, we show the non-local information is more efficient for data representation. With an implementation of a winner-take-all autoencoder, several non-local templates are trained to trace the data distribution and to represent each sample in different subspaces with a suitable weight. By training a linear model for each subspace in a divide and conquer manner, one single support vector machine can be formulated to solve nonlinear classification problems. Experimental results demonstrate that a mixture of multiple linear classifiers from non-local information performs better than or is at least competitive with state-of-the-art mixtures of locally linear models.
UR - http://www.scopus.com/inward/record.url?scp=85031040703&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85031040703&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2017.7966327
DO - 10.1109/IJCNN.2017.7966327
M3 - Conference contribution
AN - SCOPUS:85031040703
VL - 2017-May
SP - 3741
EP - 3746
BT - 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
ER -